feat(skillopt 0.5.0 + skillopt-hook 0.1.0): auto-use (hybrid) — activate + SessionStart inject#421
Merged
Merged
Conversation
…ate + SessionStart inject "자동으로" + "agent actively uses" via a USE-vs-TRAIN split: USE is automatic + opt-in + cheap; TRAIN stays a command/agent decision (cost-bearing). - 🪝 skillopt-hook 0.1.0 (new hook) — SessionStart injects the active learned skill (~/.sidecar/skillopt/active-skill.md) as additionalContext so a trained skill is applied with NO command; silent when nothing activated; never trains (cost); always exits 0 (fail-open). Optional ~/.sidecar/skillopt/agent-active marker adds a one-line nudge to PROPOSE (never auto-run) /skillopt train for repeatable scored tasks. Same command/hook split shape as prefs. - 🎓 skillopt 0.5.0 — /skillopt activate <skill.md> (write SSOT → auto-use ON) · deactivate (OFF) · agent-active on|off (toggle nudge). Verified: activate → hook emits correct JSON (hookEventName=SessionStart + skill body) · agent-active appends nudge · deactivate → empty output (silent). g22 lockstep both plugins + CHANGELOG.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
"자동으로" + "agent actively uses" via a USE-vs-TRAIN split: USE is automatic +
opt-in + cheap; TRAIN stays a command/agent decision (cost-bearing).
(~/.sidecar/skillopt/active-skill.md) as additionalContext so a trained skill is
applied with NO command; silent when nothing activated; never trains (cost);
always exits 0 (fail-open). Optional ~/.sidecar/skillopt/agent-active marker adds a
one-line nudge to PROPOSE (never auto-run) /skillopt train for repeatable scored
tasks. Same command/hook split shape as prefs.
deactivate (OFF) · agent-active on|off (toggle nudge).
Verified: activate → hook emits correct JSON (hookEventName=SessionStart + skill
body) · agent-active appends nudge · deactivate → empty output (silent).
g22 lockstep both plugins + CHANGELOG.